Activity Number:
|
230
- Recent Advances in Nonexchangeable, Dependent, Random Partition and Feature Allocation Models
|
Type:
|
Topic Contributed
|
Date/Time:
|
Monday, July 30, 2018 : 2:00 PM to 3:50 PM
|
Sponsor:
|
International Society for Bayesian Analysis (ISBA)
|
Abstract #329397
|
Presentation
|
Title:
|
Recent Advances in Dependent Random Partition Models
|
Author(s):
|
Garritt L Page* and Fernando Quintana
|
Companies:
|
Brigham Young University and Pontificia Universidad Catolica De Chile
|
Keywords:
|
spatial dependence;
nonparametric Bayes;
clustering
|
Abstract:
|
Incorporating information in random partition distributions beyond that which is contained in the parititon (i.e., cluster size) has recieved considerable interest. We present some recent results with focus placed on partitions with co-clustering probabilities that depend on space and time. Our approach is to jointly model a collection of spatially referenced partitions so that they evolve smoothly over time.
|
Authors who are presenting talks have a * after their name.